Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    instances of personal pronouns and their associated concepts in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Not only... but also

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     obfer
    -0.42
    igshid
    -0.38
    genodigd
    -0.36
     bicchiere
    -0.35
     Canoe
    -0.35
     desal
    -0.35
     propOrder
    -0.35
     Renew
    -0.34
     aufs
    -0.34
    rangea
    -0.34
    POSITIVE LOGITS
    LookAnd
    0.72
    sizeCache
    0.60
    AsUp
    0.57
     autorytatywna
    0.51
     resourceCulture
    0.50
    Autoritní
    0.49
     <<<<<<<<<<<<<<
    0.49
    addCriterion
    0.49
     betweenstory
    0.48
    RepeatedField
    0.48
    Act Density 0.011%

    No Known Activations